Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 175
    Prev
    Next
    INDEX
    Explanations

    references to charity and fundraising events or initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    390
    +0.10
    0.3%
    2011
    +0.08
    0.3%
    814
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.10
    0.02
    81
    +0.08
    0.02
    270
    +0.07
    0.02
    Negative Logits
    MessageOf
    -0.78
    SequentialGroup
    -0.73
    RTLR
    -0.69
    ുറ
    -0.66
    Enllaços
    -0.66
    HasIndex
    -0.66
    JspWriter
    -0.65
    prepareStatement
    -0.65
    ⓧ
    -0.62
    InsertCommand
    -0.62
    POSITIVE LOGITS
     maneu
    2.04
     emphat
    1.89
     increa
    1.82
     impra
    1.80
     shenan
    1.78
     affor
    1.77
     indestru
    1.74
     reluct
    1.71
     milf
    1.71
     apprehen
    1.68
    Activations Density 0.230%

    No Known Activations